Apprenez-vous les opérations sympas des pandas que 1 % des gens connaissent

>>> pd.Series._accessors
{'cat', 'str', 'dt'}复制代码

# 定义一个Series序列
>>> addr = pd.Series([
...     'Washington, D.C. 20003',
...     'Brooklyn, NY 11211-1755',
...     'Omaha, NE 68154',
...     'Pittsburgh, PA 15211'
... ]) 

>>> addr.str.upper()
0     WASHINGTON, D.C. 20003
1    BROOKLYN, NY 11211-1755
2            OMAHA, NE 68154
3       PITTSBURGH, PA 15211
dtype: object

>>> addr.str.count(r'\d') 
0    5
1    9
2    5
3    5
dtype: int64复制代码

>>> regex = (r&#39;(?P<city>[A-Za-z ]+), &#39;      # 一个或更多字母
...          r&#39;(?P<state>[A-Z]{2}) &#39;        # 两个大写字母
...          r&#39;(?P<zip>\d{5}(?:-\d{4})?)&#39;)  # 可选的4个延伸数字
...
>>> addr.str.replace(&#39;.&#39;, &#39;&#39;).str.extract(regex)
         city state         zip
0  Washington    DC       20003
1    Brooklyn    NY  11211-1755
2       Omaha    NE       68154
3  Pittsburgh    PA       15211复制代码

>>> [i for i in dir(pd.Series.str) if not i.startswith('_')]
['capitalize',
 'cat',
 'center',
 'contains',
 'count',
 'decode',
 'encode',
 'endswith',
 'extract',
 'extractall',
 'find',
 'findall',
 'get',
 'get_dummies',
 'index',
 'isalnum',
 'isalpha',
 'isdecimal',
 'isdigit',
 'islower',
 'isnumeric',
 'isspace',
 'istitle',
 'isupper',
 'join',
 'len',
 'ljust',
 'lower',
 'lstrip',
 'match',
 'normalize',
 'pad',
 'partition',
 'repeat',
 'replace',
 'rfind',
 'rindex',
 'rjust',
 'rpartition',
 'rsplit',
 'rstrip',
 'slice',
 'slice_replace',
 'split',
 'startswith',
 'strip',
 'swapcase',
 'title',
 'translate',
 'upper',
 'wrap',
 'zfill']复制代码

>>> daterng = pd.Series(pd.date_range('2017', periods=9, freq='Q'))
>>> daterng
0   2017-03-31
1   2017-06-30
2   2017-09-30
3   2017-12-31
4   2018-03-31
5   2018-06-30
6   2018-09-30
7   2018-12-31
8   2019-03-31
dtype: datetime64[ns]

>>>  daterng.dt.day_name()
0      Friday
1      Friday
2    Saturday
3      Sunday
4    Saturday
5    Saturday
6      Sunday
7      Monday
8      Sunday
dtype: object

>>> # 查看下半年
>>> daterng[daterng.dt.quarter > 2]
2   2017-09-30
3   2017-12-31
6   2018-09-30
7   2018-12-31
dtype: datetime64[ns]

>>> daterng[daterng.dt.is_year_end]
3   2017-12-31
7   2018-12-31
dtype: datetime64[ns]复制代码

>>> colors = pd.Series([
...     'periwinkle',
...     'mint green',
...     'burnt orange',
...     'periwinkle',
...     'burnt orange',
...     'rose',
...     'rose',
...     'mint green',
...     'rose',
...     'navy'
... ])
...
>>> import sys
>>> colors.apply(sys.getsizeof)
0    59
1    59
2    61
3    59
4    61
5    53
6    53
7    59
8    53
9    53
dtype: int64复制代码

>>> mapper = {v: k for k, v in enumerate(colors.unique())}
>>> mapper
{'periwinkle': 0, 'mint green': 1, 'burnt orange': 2, 'rose': 3, 'navy': 4}

>>> as_int = colors.map(mapper)
>>> as_int
0    0
1    1
2    2
3    0
4    2
5    3
6    3
7    1
8    3
9    4
dtype: int64

>>> as_int.apply(sys.getsizeof)
0    24
1    28
2    28
3    24
4    28
5    28
6    28
7    28
8    28
9    28
dtype: int64复制代码

>>> colors.memory_usage(index=False, deep=True)
650
>>> colors.astype('category').memory_usage(index=False, deep=True)
495复制代码

>>> manycolors = colors.repeat(10)
>>> len(manycolors) / manycolors.nunique() 
20.0

>>> manycolors.memory_usage(index=False, deep=True)
6500
>>> manycolors.astype('category').memory_usage(index=False, deep=True)
585复制代码

>>> ccolors = colors.astype('category')
>>> ccolors.cat.categories
Index(['burnt orange', 'mint green', 'navy', 'periwinkle', 'rose'], dtype='object')复制代码

>>> ccolors.cat.reorder_categories(mapper).cat.codes
0    0
1    1
2    2
3    0
4    2
5    3
6    3
7    1
8    3
9    4
dtype: int8复制代码

>>> [i for i in dir(ccolors.cat) if not i.startswith('_')]
['add_categories',
 'as_ordered',
 'as_unordered',
 'categories',
 'codes',
 'ordered',
 'remove_categories',
 'remove_unused_categories',
 'rename_categories',
 'reorder_categories',
 'set_categories']复制代码

>>> ccolors.iloc[5] = 'a new color'
# ...
ValueError: Cannot setitem on a Categorical with a new category,
set the categories first

>>> ccolors = ccolors.cat.add_categories(['a new color'])
>>> ccolors.iloc[5] = 'a new color'  
复制代码